Cover Image

BASIS: Balanced Activation Sketching with Invariant Scalars for "Ghost Backpropagation"

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Khasia, Vladimer
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression
by: Khasia, Vladimer
Published: (2026)

Hybrid Dual-Path Linear Transformations for Efficient Transformer Architectures
by: Khasia, Vladimer
Published: (2026)

Spectral-Window Hybrid (SWH)
by: Khasia, Vladimer
Published: (2026)

HoloByte: Continuous Hyperspherical Distillation for Tokenizer-Free Modeling
by: Khasia, Vladimer
Published: (2026)

Beyond Attention: True Adaptive World Models via Spherical Kernel Operator
by: Khasia, Vladimer
Published: (2026)

The Adaptive Vekua Cascade: A Differentiable Spectral-Analytic Solver for Physics-Informed Representation
by: Khasia, Vladimer
Published: (2025)

DeepVekua: Geometric-Spectral Representation Learning for Physics-Informed Fields
by: Khasia, Vladimer
Published: (2025)

Dynamic Subspace Composition: Efficient Adaptation via Contractive Basis Expansion
by: Khasia, Vladimer
Published: (2025)

The Vekua Layer: Exact Physical Priors for Implicit Neural Representations via Generalized Analytic Functions
by: Khasia, Vladimer
Published: (2025)

Primal: A Unified Deterministic Framework for Quasi-Orthogonal Hashing and Manifold Learning
by: Khasia, Vladimer
Published: (2025)

Less Memory Means smaller GPUs: Backpropagation with Compressed Activations
by: Barley, Daniel, et al.
Published: (2024)

Comprehensive Survey of Complex-Valued Neural Networks: Insights into Backpropagation and Activation Functions
by: Hammad, M. M.
Published: (2024)

Backpropagation Neural Tree
by: Ojha, Varun, et al.
Published: (2022)

The Cost of Avoiding Backpropagation
by: Panchal, Kunjal, et al.
Published: (2025)

Practical Boolean Backpropagation
by: Golbert, Simon
Published: (2025)

Efficient Deep Learning with Decorrelated Backpropagation
by: Dalm, Sander, et al.
Published: (2024)

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
by: Yun, Vincent-Daniel, et al.
Published: (2026)

THDC: Training Hyperdimensional Computing Models with Backpropagation
by: Dejonghe, Hanne, et al.
Published: (2026)

Towards Scalable Backpropagation-Free Gradient Estimation
by: Wang, Daniel, et al.
Published: (2025)

Efficient Backpropagation with Variance-Controlled Adaptive Sampling
by: Wang, Ziteng, et al.
Published: (2024)

BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning
by: Gong, Shijin, et al.
Published: (2026)

Backpropagation on Dynamical Networks
by: Tan, Eugene, et al.
Published: (2022)

Unbiased Approximate Vector-Jacobian Products for Efficient Backpropagation
by: Bakong, Killian, et al.
Published: (2026)

Can Local Learning Match Self-Supervised Backpropagation?
by: Zihan, Wu S., et al.
Published: (2026)

Fast and Interpretable Autoregressive Estimation with Neural Network Backpropagation
by: Lucena, Anaísa, et al.
Published: (2026)

Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencoder
by: Koune, Ioannis Christoforos, et al.
Published: (2025)

Backpropagation through Combinatorial Algorithms: Identity with Projection Works
by: Sahoo, Subham Sekhar, et al.
Published: (2022)

Unlocked Backpropagation using Wave Scattering
by: Pehle, Christian, et al.
Published: (2026)

Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation
by: Zhang, Tianyi, et al.
Published: (2024)

PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels
by: Kacham, Praneeth, et al.
Published: (2023)

Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
by: Sójka, Damian, et al.
Published: (2026)

Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency
by: Zhang, Yibo Jacky, et al.
Published: (2026)

LBI: Parallel Scan Backpropagation via Latent Bounded Interfaces
by: Lee, Shaun Christopher, et al.
Published: (2026)

Backpropagation-Free Metropolis-Adjusted Langevin Algorithm
by: Cobb, Adam D., et al.
Published: (2025)

Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels
by: Ahmad, Tamim El, et al.
Published: (2023)

LPGD: A General Framework for Backpropagation through Embedded Optimization Layers
by: Paulus, Anselm, et al.
Published: (2024)

Optimal Control Theoretic Neural Optimizer: From Backpropagation to Dynamic Programming
by: Liu, Guan-Horng, et al.
Published: (2025)

Training Implicit Networks for Image Deblurring using Jacobian-Free Backpropagation
by: Liu, Linghai, et al.
Published: (2024)

Stabilizing Backpropagation in 16-bit Neural Training with Modified Adam Optimizer
by: Yun, Juyoung
Published: (2023)

Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams
by: Feng, Yuan, et al.
Published: (2025)